List your company

Medical Question Answering on MedQA (MAE)

0.038MAEEnsemble
0.022720.125860.2290.33214May 8, 2026

Evaluation results

MethodLinks
EnsembleNum. queries=64, Evaluation protocol=Leave-One-Family-Out protocol2026.050.038
DKPSNum. queries=64, Evaluation protocol=Leave-One-Family-Out protocol2026.050.039
Sample ScoreNum. queries=64, Evaluation protocol=Leave-One-Family-Out protocol2026.050.044
EnsembleNum. queries=16, Evaluation protocol=Leave-One-Family-Out protocol2026.050.065
DKPSNum. queries=16, Evaluation protocol=Leave-One-Family-Out protocol2026.050.066
Sample ScoreNum. queries=16, Evaluation protocol=Leave-One-Family-Out protocol2026.050.093
DKPSNum. queries=4, Evaluation protocol=Leave-One-Family-Out protocol2026.050.094
EnsembleNum. queries=4, Evaluation protocol=Leave-One-Family-Out protocol2026.050.094
DKPSNum. queries=1, Evaluation protocol=Leave-One-Family-Out protocol2026.050.121
EnsembleNum. queries=1, Evaluation protocol=Leave-One-Family-Out protocol2026.050.121
Pop. MeanNum. queries=1, Evaluation protocol=Leave-One-Family-Out protocol2026.050.131
Pop. MeanNum. queries=4, Evaluation protocol=Leave-One-Family-Out protocol2026.050.131
Pop. MeanNum. queries=16, Evaluation protocol=Leave-One-Family-Out protocol2026.050.131
Pop. MeanNum. queries=64, Evaluation protocol=Leave-One-Family-Out protocol2026.050.131
Sample ScoreNum. queries=4, Evaluation protocol=Leave-One-Family-Out protocol2026.050.189
Sample ScoreNum. queries=1, Evaluation protocol=Leave-One-Family-Out protocol2026.050.42